virtio_blk: set the zone write granularitygrafted

virtblk_read_zoned_limits() reads the write granularity that the device
reports in virtio_blk_zoned_characteristics and assigns it to the
physical block size and to io_min, but never to the limit that is named
after it. queue_limits.zone_write_granularity is left at zero, so
blk_validate_zoned_limits() raises it to the logical block size:

	if (lim->zone_write_granularity < lim->logical_block_size)
		lim->zone_write_granularity = lim->logical_block_size;

A device that reports a granularity coarser than its logical block size,
which is what the field exists to express, therefore has it silently
reduced. A 512e host managed disk passed through to a guest reports a
logical block size of 512 and a write granularity of 4096, and the guest
ends up with a zone write granularity of 512.

bio_split_alignment() returns lim->zone_write_granularity if it is non-zero
and bio_split_io_at() may split a bio with as per bio_split_alignment().
This can real to the write getting rejected by the host drive, as the write
is not aligned to the physical block size.

zonefs also takes its block size from bdev_zone_write_granularity(), so it
would incorrectly use 512 on a disk that requires 4096.

sd_zbc_read_zones() sets the limit from the physical block size for the
same reason. NVMe ZNS and null_blk leave it unset, but the fallback
gives the right answer for them, as their write granularity is the
logical block size. virtio carries a separate value that may exceed it.

Set the zone write granularity from the value that the device reports.

Fixes: 95bfec41bd3d ("virtio-blk: add support for zoned block devices")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://patch.msgid.link/20260918140641.2031075-2-cassel@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 156 insertions, 0 deletions

diff --git a/block/partitions/atari.c b/block/partitions/atari.c
new file mode 100644
index 000000000..2438d1448
--- /dev/null
+++ b/block/partitions/atari.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  fs/partitions/atari.c
+ *
+ *  Code extracted from drivers/block/genhd.c
+ *
+ *  Copyright (C) 1991-1998  Linus Torvalds
+ *  Re-organised Feb 1998 Russell King
+ */
+
+#include <linux/ctype.h>
+#include "check.h"
+#include "atari.h"
+
+/* ++guenther: this should be settable by the user ("make config")?.
+ */
+#define ICD_PARTS
+
+/* check if a partition entry looks valid -- Atari format is assumed if at
+   least one of the primary entries is ok this way */
+#define	VALID_PARTITION(pi,hdsiz)					     \
+    (((pi)->flg & 1) &&							     \
+     isalnum((pi)->id[0]) && isalnum((pi)->id[1]) && isalnum((pi)->id[2]) && \
+     be32_to_cpu((pi)->st) <= (hdsiz) &&				     \
+     be32_to_cpu((pi)->st) + be32_to_cpu((pi)->siz) <= (hdsiz))
+
+static inline int OK_id(char *s)
+{
+	return  memcmp (s, "GEM", 3) == 0 || memcmp (s, "BGM", 3) == 0 ||
+		memcmp (s, "LNX", 3) == 0 || memcmp (s, "SWP", 3) == 0 ||
+		memcmp (s, "RAW", 3) == 0 ;
+}
+
+int atari_partition(struct parsed_partitions *state)
+{
+	Sector sect;
+	struct rootsector *rs;
+	struct partition_info *pi;
+	u32 extensect;
+	u32 hd_size;
+	int slot;
+#ifdef ICD_PARTS
+	int part_fmt = 0; /* 0:unknown, 1:AHDI, 2:ICD/Supra */
+#endif
+
+	/*
+	 * ATARI partition scheme supports 512 lba only.  If this is not
+	 * the case, bail early to avoid miscalculating hd_size.
+	 */
+	if (queue_logical_block_size(state->disk->queue) != 512)
+		return 0;
+
+	rs = read_part_sector(state, 0, &sect);
+	if (!rs)
+		return -1;
+
+	/* Verify this is an Atari rootsector: */
+	hd_size = get_capacity(state->disk);
+	if (!VALID_PARTITION(&rs->part[0], hd_size) &&
+	    !VALID_PARTITION(&rs->part[1], hd_size) &&
+	    !VALID_PARTITION(&rs->part[2], hd_size) &&
+	    !VALID_PARTITION(&rs->part[3], hd_size)) {
+		/*
+		 * if there's no valid primary partition, assume that no Atari
+		 * format partition table (there's no reliable magic or the like
+	         * :-()
+		 */
+		put_dev_sector(sect);
+		return 0;
+	}
+
+	pi = &rs->part[0];
+	seq_buf_puts(&state->pp_buf, " AHDI");
+	for (slot = 1; pi < &rs->part[4] && slot < state->limit; slot++, pi++) {
+		struct rootsector *xrs;
+		Sector sect2;
+		ulong partsect;
+
+		if ( !(pi->flg & 1) )
+			continue;
+		/* active partition */
+		if (memcmp (pi->id, "XGM", 3) != 0) {
+			/* we don't care about other id's */
+			put_partition (state, slot, be32_to_cpu(pi->st),
+					be32_to_cpu(pi->siz));
+			continue;
+		}
+		/* extension partition */
+#ifdef ICD_PARTS
+		part_fmt = 1;
+#endif
+		seq_buf_puts(&state->pp_buf, " XGM<");
+		partsect = extensect = be32_to_cpu(pi->st);
+		while (1) {
+			xrs = read_part_sector(state, partsect, &sect2);
+			if (!xrs) {
+				printk (" block %ld read failed\n", partsect);
+				put_dev_sector(sect);
+				return -1;
+			}
+
+			/* ++roman: sanity check: bit 0 of flg field must be set */
+			if (!(xrs->part[0].flg & 1)) {
+				printk( "\nFirst sub-partition in extended partition is not valid!\n" );
+				put_dev_sector(sect2);
+				break;
+			}
+
+			put_partition(state, slot,
+				   partsect + be32_to_cpu(xrs->part[0].st),
+				   be32_to_cpu(xrs->part[0].siz));
+
+			if (!(xrs->part[1].flg & 1)) {
+				/* end of linked partition list */
+				put_dev_sector(sect2);
+				break;
+			}
+			if (memcmp( xrs->part[1].id, "XGM", 3 ) != 0) {
+				printk("\nID of extended partition is not XGM!\n");
+				put_dev_sector(sect2);
+				break;
+			}
+
+			partsect = be32_to_cpu(xrs->part[1].st) + extensect;
+			put_dev_sector(sect2);
+			if (++slot == state->limit) {
+				printk( "\nMaximum number of partitions reached!\n" );
+				break;
+			}
+		}
+		seq_buf_puts(&state->pp_buf, " >");
+	}
+#ifdef ICD_PARTS
+	if ( part_fmt!=1 ) { /* no extended partitions -> test ICD-format */
+		pi = &rs->icdpart[0];
+		/* sanity check: no ICD format if first partition invalid */
+		if (OK_id(pi->id)) {
+			seq_buf_puts(&state->pp_buf, " ICD<");
+			for (; pi < &rs->icdpart[8] && slot < state->limit; slot++, pi++) {
+				/* accept only GEM,BGM,RAW,LNX,SWP partitions */
+				if (!((pi->flg & 1) && OK_id(pi->id)))
+					continue;
+				put_partition (state, slot,
+						be32_to_cpu(pi->st),
+						be32_to_cpu(pi->siz));
+			}
+			seq_buf_puts(&state->pp_buf, " >");
+		}
+	}
+#endif
+	put_dev_sector(sect);
+
+	seq_buf_puts(&state->pp_buf, "\n");
+
+	return 1;
+}